ClawHub

A股-加密货币-定时早报-多维度指标全方位分析-安装即用无复杂配置-自带验证降低幻觉

Security checks across malware telemetry and agentic risk

Overview

This is a coherent market-analysis skill with disclosed, user-run data-fetch scripts and no evidence of hidden account actions, persistence, or data theft.

Install only if you want a finance research/reporting skill that can call public market-data services. Run the Python scripts intentionally in a local virtual environment, review dependencies before installing, keep CryptoPanic tokens out of chat logs, and treat generated trading reports as research rather than financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
# Install deps
    subprocess.check_call([str(py), "-m", "pip", "install", "-U", "pip"])
    subprocess.check_call([str(py), "-m", "pip", "install", "-r", str(req)])

    print("ok")
    print(f"venv: {venv_dir}")
Confidence
91% confidence
Finding
subprocess.check_call([str(py), "-m", "pip", "install", "-r", str(req)])

Tainted flow: 'url' from os.getenv (line 573, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Content
f"auth_token={token}&public=true&currencies={base_symbol}&kind={kind}"
    )
    try:
        resp = requests.get(url, timeout=10)
    except requests.RequestException:
        raise RuntimeError("CryptoPanic request failed") from None
Confidence
97% confidence
Finding
resp = requests.get(url, timeout=10)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation text uses very broad trigger phrases such as any mention of crypto, A-shares, strategies, stop loss, targets, win rate, drawdown, and morning brief, which overlap with common financial discussion. Overbroad triggers are risky because they can cause unintended automatic loading in unrelated contexts, increasing the chance that the skill influences responses, requests tools, or accesses data when the user did not clearly ask for this workflow.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The 'When to use' section remains ambiguously scoped and includes expansive categories like structured market data, dual-market view, trading plans, order book, funding, and OI, without clear boundary conditions. In context, this makes the skill more dangerous because it is designed to steer outputs into rigid financial advice templates and could activate for many normal finance-related prompts, potentially overriding safer general handling or causing unnecessary tool/data use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal